© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117670
    Prev
    Next
    INDEX
    Explanations

    hippocampal structures and function

    np_acts-logits-general · gemini-2.5-flash-lite

    references to specific brain regions, particularly the hippocampus and related structures like the dentate gyrus.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    зион
    -0.78
    plained
    -0.73
    жка
    -0.73
     음
    -0.69
    ąć
    -0.68
    ítez
    -0.67
    ITHER
    -0.66
     броса
    -0.66
     Catar
    -0.66
     Grove
    -0.65
    POSITIVE LOGITS
     hippocampal
    1.62
     hippocampus
    1.44
    hippo
    1.24
     Hippo
    1.14
    Hippo
    1.10
     dent
    1.03
     hipo
    0.98
    dent
    0.98
    spatial
    0.97
     memory
    0.96
    Activations Density 0.111%

    No Known Activations